Better shot-scraper har -x -o, closes #187

https://gistpreview.github.io/?631b4354484f900828266780384c7790

Author: simonw

docs/har.md

@@ -104,7 +104,13 @@ Usage: shot-scraper har [OPTIONS] URL
   Use --zip to save as a .har.zip file instead, or specify a filename ending in
   .har.zip
 
-  Use --extract / -x to also extract all resources from the HAR into a directory
+  Use --extract / -x to also extract all resources from the HAR into a
+  directory. With -x, you can specify a base path and the .har extension will be
+  added automatically:
+
+      shot-scraper har https://datasette.io/ -x -o /tmp/datasette
+
+  This creates /tmp/datasette.har and extracts resources to /tmp/datasette/
 
 Options:
   -z, --zip              Save as a .har.zip file

shot_scraper/cli.py

@@ -782,12 +782,20 @@ def har(
 
     Use --zip to save as a .har.zip file instead, or specify a filename ending in .har.zip
 
-    Use --extract / -x to also extract all resources from the HAR into a directory
+    Use --extract / -x to also extract all resources from the HAR into a directory.
+    With -x, you can specify a base path and the .har extension will be added automatically:
+
+        shot-scraper har https://datasette.io/ -x -o /tmp/datasette
+
+    This creates /tmp/datasette.har and extracts resources to /tmp/datasette/
     """
     if output is None:
         output = filename_for_url(
             url, ext="har.zip" if zip_ else "har", file_exists=os.path.exists
         )
+    elif extract and not (output.endswith(".har") or output.endswith(".har.zip")):
+        # When -x is used with -o that lacks .har extension, treat as base path
+        output = output + (".har.zip" if zip_ else ".har")
 
     url = url_or_file_path(url, _check_and_absolutize)
     with sync_playwright() as p:

tests/test_shot_scraper.py

@@ -354,6 +354,8 @@ def test_multi_har(http_server, args, expect_zip, record_shots):
         (["-x", "-z"], True),
         (["--extract", "-o", "output.har"], False),
         (["-x", "-o", "output.har.zip"], True),
+        (["--extract", "-o", "basepath"], False),  # base path without extension
+        (["-x", "-z", "-o", "basepath"], True),  # base path with zip
     ),
 )
 def test_har_extract(http_server, args, expect_zip):